Possibly Useful Books:

 

Chater and Manning (2006) include a broad overview of work on different sorts of linguistic processes and the divide between Chomskyan and computational linguists.  They mention how computational work on language acquisition its in its infancy and little work of note has been achieve in most areas. "By contrast, many simple but important aspects of language structure have successfully been learned from linguistic corpora by distribution methods.  For example, good approximations to syntactic categories and semantic classes have been learned by clustering words based on their linear distribution contexts (e.g. the distribution over the word that precedes and follows each token of a type) or broad topical contexts (e.g. Schuetze 1995 and Redington 1998); see Figure 2.  One can even simultaneously cluster words exploiting local syntactic and topical similarity (Griffiths 2004).

(Figure 2 shows use of two context words on each side of a word, and an associated hierarchically built-up tree that successfully captures semantic categories within the overall semantic category of NOUN/ADJ.)

In general, the other works by Redington are probably all good.

 

All works:

 

Literature\Biemann - c. 2006 - Ontology Learning from Text A Survey of Methods.pdf

Literature\Brown et al - 1992 - Class-Based n-Gram Models of Natural Language.pdf

Literature\Chater, Manning - 2006 - Probabilistic models of language processing and acquisition.pdf

Literature\Clark - 2000 - Inducing syntactic categories by context distribution clustering.pdf

Literature\Clark - 2003 - Combining Distributional and Morphological Information for Part of Speech Induction.pdf

Literature\Dagan, Lee, Pereira - 1999 - Similarity-Based Models of Word Cooccurrence Probabilities.pdf

Literature\Finch, Chater, Redington - c. 1994 - Acquiring syntactic information from distributional statisti.pdf

Literature\Freitag - 2004 - Towards unsupverised whole-corpus tagging.pdf

Literature\Gamallo et al - 2004 - Divide-conquer approach to acquire syntactic categories.pdf

Literature\Griffiths et al - 2004 - Integrating Topics and Syntax.pdf

Literature\Hindle - 1990 - noun-classification-from-predicate-argument-structures.pdf

Literature\Jones - 2005 - PhD - Learning to Extract Entities from Labeled and Unlabeled Text.pdf

Literature\McMahon - 1994 - PhD - Statistical language processing based on self-organizing word classification.pdf

Literature\Oates - 1999 - Using syntax to learn semantics An experiment in language acquisition with a mobile robot.pdf

Literature\PCA-tutorial.pdf

Literature\Pereira et al - 1993 - Distributional clustering of  English words.pdf

Literature\Rada - 2003 - The Role of Non-Ambiguous Words in Natural Language Disambiguation.pdf

Literature\Redington - 1997 - Probabilistic and Distribution Approaches to Language Acquisition.pdf

Literature\Redington, Chafer, Finch - 1998 - Distributional Information a powerful cue for acquiring synt.pdf

Literature\Redington, Chater - 1998 - Connectionist and Statistical Approaches to Language Acquisition A Distributional Perspective.pdf

Literature\Redington, Chater, Finch - 1993 - distributional-information-and-acquisition-of-linguistics-categories-statistical-approach.pdf

Literature\Ritter, Hearne, Nelson - 2006 - distributional-word-clustering-in-parallel.pdf

Literature\Schuetze - 1992 - part-of-speech-induction-from-scratch.pdf

Literature\Schuetze - 1995 - Distributional POS tagging.pdf

Literature\Schultze im Walde, Brew - 2002 - Inducing German Semantic Verb Classes from Purely Syntactic Subcategorisation Information.pdf

Literature\Stevenson, Joanis - 2003 - Semi-supervised Verb Class Discovery Using Noisy Features.pdf

Literature\Thelen - 2002 - A Bootstrapping Method for Learning Semantic Lexicons using Extraction Pattern Contexts.pdf

Literature\Zaanen - 1999 - Bootstrapping structure using similarity.pdf